policy-redraft

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill manages file access through a restricted directory structure at ~/.claude/plugins/config/ and provides clear proposal-only workflows to prevent unintended document modification.
  • [PROMPT_INJECTION]: Explicit guardrails are implemented within the skill instructions to prevent the agent from following user prompts that would bypass legal review or automatically apply changes to source documents.
  • [COMMAND_EXECUTION]: Tool usage is confined to research and search capabilities for verifying the status of regulatory rules, which does not involve executing arbitrary or untrusted code.
  • [DATA_EXFILTRATION]: No evidence of unauthorized network connectivity or exfiltration of sensitive information was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — policy-redraft